[{"data":1,"prerenderedAt":399},["ShallowReactive",2],{"project-32943224":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":10,"maker":11,"posted_at":12,"year":13,"points":14,"comments":15,"rank_in_year":16,"shown_in_year":17,"top":18,"tier":19,"category":20,"subcategory":21,"format":22,"keywords":23,"reception":27,"sentiment":28,"stance_mix":29,"scored_comments":34,"aspects":35,"strip":43,"post_text":46,"what":47,"said":86,"maker_in_thread":173,"shape":181,"grid":186,"attempts":361,"same_week":362,"maker_shows":40,"maker_hidden":391,"reader_version":392,"card":393},"32943224","Open Prompts","dataset of 10M Stable Diffusion generations","title","Show HN: Open Prompts – dataset of 10M Stable Diffusion generations","https:\u002F\u002Fgithub.com\u002Fkrea-ai\u002Fopen-prompts","github.com","vipermu",1663873397,2022,279,71,156,2570,7,"legend","data","prompt dataset","dataset",[24,21,25,26],"stable diffusion dataset","text to image prompts","clip search","curious",0.137,{"positive":30,"neutral":31,"mixed":32,"critical":33},8,20,0,2,30,{"idea":36,"docs":38,"design":39,"performance":41,"execution":42},{"positive":37,"critical":32},4,{"positive":32,"critical":32},{"positive":32,"critical":40},1,{"positive":32,"critical":40},{"positive":40,"critical":32},[32,44,32,32,32,32,32,32,32,32,32,44,44,32,32,32,44,32,45,32,45,45,45,44,45,45,32,40,45,45,45,45,45,45,44,32,40,44,32,44],5,3,"Open Prompts is the dataset used to build krea.ai. The data comes from the Stability AI Discord and includes around 10M images from 2M prompts. You can use it for creating semantic search engines of prompts, training LLMs, fine-tuning image-to-text models like BLIP, or extracting insights from the data—like the most common combinations of modifiers.",{"problem":48,"audience":54,"pricing":55,"motivation":61,"time_to_build":54,"stack":68,"openness":83,"stage":84,"team_size":85},{"value":49,"source":50,"evidence":51},"Provides a large public collection of Stable Diffusion prompts and images for search, training and analysis","maker",[52],{"id":53},"post",null,{"value":56,"source":50,"evidence":57},"free",[58],{"id":59,"by":11,"text":60},"32944563","Thanks! Great work with Lexica. We also released a free API https:\u002F\u002Fdevapi.krea.ai\u002F if anyone wants to check it out. It will soon have endpoints with custom image generation…",{"value":62,"source":50,"evidence":63},"Enable semantic prompt search, model training and studies of AI image generation",[64,65],{"id":53},{"id":66,"by":11,"text":67},"32944004","Thanks! Prompts can be hard to create, we hope that having access to these kinds of datasets we will be able to create tools and conduct studies that help us create better images…",[69,77],{"value":70,"source":71,"evidence":72},"PostgreSQL","commenter",[73],{"id":74,"by":75,"text":76},"32943742","dvrp","Krea dev here. Lexica is a search engine (like krea.ai), but it doesn’t allow you to create collections or like generations. Regarding the API, both have public APIs although I’m…",{"value":78,"source":71,"evidence":79},"Svelte and SvelteKit",[80],{"id":81,"by":75,"text":82},"32949666","I know! I’m sorry that it doesn’t work that way. The site is using Svelte + SvelteKit and I couldn’t find amazing Masonry components (like Masonic from React) that allow me to…","open_source","launched","team",{"praise":87,"objections":114,"requests":126,"questions":139,"alternatives":154},[88,103],{"value":89,"source":71,"evidence":90},"Useful free dataset and open approach",[91,95,99],{"id":92,"by":93,"text":94},"32943906","Oras","This is fantastic. A few days ago I was checking PromptBase [0] and thought it was a really good idea. Yours just took it to the next level being free with massive amount of…",{"id":96,"by":97,"text":98},"32944874","nextaccountic","This is fantastic, thanks for publishing it. I'm glad many players in the Stable Diffusion ecosystem is striving for openness (not only of the model itself but there are also…",{"id":100,"by":101,"text":102},"32945731","pwillia7","It is truly crazy the pace of updates. It's the first single topic I feel like I can't keep up with no matter how much time I spend with it. It's like how they say Da Vinci's was…",{"value":104,"source":71,"evidence":105},"Good for finding prompts and combinations",[106,110],{"id":107,"by":108,"text":109},"32945062","tgtweak","Great work on Lexica.art, it's been indispensable for finding good prompts and combinations. How much does it cost to host it? Feels like hosting 500GB of images and serving them…",{"id":111,"by":112,"text":113},"32947040","mod","Wish the back button could find my spot on the page. Fun to explore the prompts getting results similar to what I want. Great project.",[115,122],{"value":116,"source":71,"evidence":117},"Faces and people look like horror",[118],{"id":119,"by":120,"text":121},"32948314","ipaddr","When it comes to faces or people all photos default to horror.",{"value":123,"source":71,"evidence":124},"Back button does not restore scroll position",[125],{"id":111,"by":112,"text":113},[127,133],{"value":128,"source":71,"evidence":129},"Record which Stable Diffusion version generated each image",[130],{"id":131,"by":97,"text":132},"32945249","Hey, was the specific Stable Diffusion version used to generate each image recorded anywhere in the dataset? In krea.ai, it doesn't say which version of the model was used to…",{"value":134,"source":71,"evidence":135},"Add 1.4 images to the dataset",[136],{"id":137,"by":97,"text":138},"32948678","Could you somehow indicate this in the web ui of krea.ai? Maybe when there are more versions (Why aren't 1.4 images part of the dataset? Someone said they are public too)",[140,147],{"value":141,"source":71,"evidence":142},"How was the data scraped from Discord",[143],{"id":144,"by":145,"text":146},"32945421","masterspy7","I'm curious, I've seen a few sites like this which grab from the Stability Discord. Is there a way to quickly scrape this amount of data from a Discord server?",{"value":148,"source":71,"evidence":149},"How does it compare with Lexica",[150],{"id":151,"by":152,"text":153},"32943643","cercatrova","How does it compare with https:\u002F\u002Flexica.art?",[155,163,167],{"value":156,"source":71,"evidence":157},"Lexica",[158,159],{"id":151,"by":152,"text":153},{"id":160,"by":161,"text":162},"32945037","jaimex2","There's also https:\u002F\u002Flexica.art\u002F",{"value":164,"source":71,"evidence":165},"PromptBase",[166],{"id":92,"by":93,"text":94},{"value":168,"source":71,"evidence":169},"OpenArt, PromptHero and other prompt sites",[170],{"id":171,"by":75,"text":172},"32946551","And OpenArt, PromptBase, PromptHero, Libraire… and who knows how many more will pop up in the next months… or shall I say hours ;-)?",{"comments":174,"answered":44,"key":175},13,[176,177,180],{"id":59,"text":60},{"id":178,"text":179},"32945885","really cool! that must have been a lot of work. Here's another great site for references:…",{"id":66,"text":67},{"commenters":182,"max_depth":183,"maker_replies":174,"first_comment_mins":184,"lifespan_hours":185},35,6,10,15,[187,191,193,197,198,200,203,206,209,211,214,218,222,225,228,231,232,235,237,239,241,243,246,249,250,253,256,258,261,262,264,265,267,271,273,276,278,280,282,284,285,287,290,292,296,298,300,304,306,308,310,312,314,316,317,319,321,324,326,328,332,334,336,339,342,345,348,350,352,353,358],[188,32,32,189,190,32],"32944455","other\u002Fneutral\u002Fnone","Samin100",[59,32,32,192,11,40],"project\u002Fneutral\u002Fnone",[194,32,44,195,196,32],"32947541","project\u002Fpositive\u002Fnone","edreismd",[107,32,32,189,108,32],[199,32,32,189,190,32],"32945408",[201,32,32,189,202,32],"32946002","indigodaddy",[204,32,32,189,205,32],"32947037","RandomBK",[207,32,32,189,208,32],"32949500","capableweb",[210,32,32,189,75,32],"32946360",[212,32,32,189,213,32],"32948340","johndough",[215,32,32,216,217,32],"32948638","other\u002Fneutral\u002Fpricing","avereveard",[219,32,32,220,221,32],"32945473","other\u002Fneutral\u002Fdesign","Lerc",[223,32,32,224,75,32],"32946367","other\u002Fneutral\u002Fidea",[226,32,32,227,196,32],"32947533","other\u002Fpositive\u002Fnone",[229,40,32,189,230,32],"32945819","password4321",[178,40,32,227,11,40],[233,40,32,189,234,32],"32946377","davidbarker",[236,40,32,189,112,32],"32947063",[238,40,32,189,234,32],"32946370",[240,40,32,227,75,32],"32949698",[92,33,44,242,93,32],"project\u002Fpositive\u002Fidea",[244,33,45,245,75,32],"32943923","maker\u002Fneutral\u002Fnone",[247,33,44,195,248,32],"32945841","ionwake",[66,33,32,242,11,40],[251,33,32,216,252,32],"32950073","tasuki",[254,45,32,189,255,32],"32944086","whalesalad",[257,45,32,189,11,40],"32944905",[259,45,32,189,260,32],"32945516","dr_dshiv",[96,37,44,242,97,32],[263,37,32,189,11,40],"32945026",[100,37,32,189,101,32],[266,37,32,189,75,32],"32946379",[268,44,45,269,270,32],"32944410","project\u002Fneutral\u002Fdocs","davidkunz",[272,44,32,269,11,40],"32944591",[274,183,32,189,275,32],"32949875","smusamashah",[151,18,45,277,152,32],"project\u002Fneutral\u002Fidea",[279,18,32,192,11,40],"32943677",[281,18,45,269,196,32],"32947590",[283,18,45,269,75,32],"32949645",[74,18,45,192,75,32],[286,18,44,195,196,32],"32947583",[288,30,45,277,289,32],"32949336","maaaaattttt",[291,30,45,277,75,32],"32949682",[293,294,45,277,295,32],"32943891",9,"rhacker",[297,294,45,277,75,32],"32943929",[299,294,32,192,11,40],"32943982",[301,294,32,302,303,32],"32944434","commenter\u002Fneutral\u002Fidea","mgraczyk",[111,184,40,305,112,32],"project\u002Fcritical\u002Fdesign",[81,184,45,307,75,32],"project\u002Fneutral\u002Fdesign",[144,309,45,192,145,32],11,[311,309,45,192,75,32],"32946394",[131,313,45,192,97,32],12,[315,313,32,192,11,40],"32945845",[137,313,45,307,97,32],[318,313,45,192,75,32],"32948767",[320,313,45,192,75,32],"32946402",[322,174,45,277,323,32],"32945386","hwers",[325,174,32,192,11,40],"32945441",[327,174,32,189,323,32],"32946647",[329,330,45,277,331,32],"32944404",14,"jononor",[333,330,32,269,11,40],"32944857",[335,330,44,242,97,32],"32945095",[337,330,32,302,338,32],"32945205","alecdibble",[340,185,45,277,341,32],"32946767","XorNot",[119,343,40,344,120,32],16,"project\u002Fcritical\u002Fperformance",[346,347,44,242,260,32],"32945231",17,[349,347,32,307,11,40],"32945276",[160,351,32,189,161,32],18,[171,351,32,189,75,32],[354,355,44,356,357,32],"32943361",19,"project\u002Fpositive\u002Fexecution","Philomath",[359,355,32,360,11,40],"32943596","project\u002Fneutral\u002Fexecution",[],[363,368,373,377,381,386],{"id":364,"name":365,"points":366,"category":367},"32993130","Quazel",787,"learning_science",{"id":369,"name":370,"points":371,"category":372},"32939407","Dub",255,"dev_tools",{"id":374,"name":375,"points":376,"category":372},"32941613","Ezno",175,{"id":378,"name":379,"points":380,"category":372},"32935506","Rocketry",168,{"id":382,"name":383,"points":384,"category":385},"32976832","muted.io guitar chords",157,"languages",{"id":387,"name":388,"points":389,"category":390},"32962524","Jot",146,"productivity",false,"v2",{"id":394,"name":5,"line":6,"ai":391,"cat":20,"year":13,"points":14,"comments":15,"rec":27,"s":395,"top":18,"kw":396,"maker":11,"domain":10,"tier":19,"attempts":32,"strip":397,"url":9,"mix":398,"praise":89,"objection":116,"sub":21},32943224,0.14,[24,21,25,26],"0500000000055000503033353301333333501505",[30,31,32,33],1794036625417]